A method, a computer system, and a computer program product for detecting voice commands. Audio is recorded by the computer system to form a recorded audio. The computer system then determines whether a voice command spoken by a first person is present in the recorded audio. If the voice command is present in the recorded audio, the computer system determines whether the voice command is directed to a second person by the first person. If the voice command is not being directed to the second person, the computer system processes the voice command, wherein processing of the voice command occurs without a wake word.
Legal claims defining the scope of protection, as filed with the USPTO.
1. A method for detecting voice commands, the method comprising: recording, by a computer system, audio to form a recorded audio; converting, by the computer system, the recorded audio to text using voice-to-text conversion; performing, by the computer system, a comparison of the text of the voice-to-text conversion to keywords for queries using fuzzy logic to determine whether a voice command is spoken by a first person in the recorded audio; identifying, by the computer system, the voice command spoken by the first person in the recorded audio based on the comparison; determining, by the computer system, whether the voice command spoken by the first person is directed to a virtual assistant without using a wake word to activate the virtual assistant and not to a second person by evaluating the voice command for specific language qualifiers indicative of the voice command not referencing the second person; and responsive to the voice command not referencing the second person, processing, by the computer system, the voice command using the virtual assistant without the wake word.
2. The method of claim 1 , wherein the specific language qualifiers are selected from at least one of the first person asking a question without referencing anyone, the first person issuing the voice command without referencing anyone, or the first person asking for an interface with an Internet of things device without referencing anyone.
3. The method of claim 1 , wherein recording, by the computer system, the audio to form the recorded audio comprises: recording, by the computer system, the audio in a circular buffer.
4. The method of claim 1 , wherein recording, by the computer system, the audio to form the recorded audio comprises: recording the audio to form the recorded audio using a listening device in the computer system.
5. The method of claim 4 , wherein the listening device is selected from a group comprising a smart speaker, a mobile phone, a tablet computer, a television, a digital media player, a refrigerator, and an Internet appliance.
6. A computer system for detecting voice commands, the computer system comprising: a bus system; a storage device connected to the bus system, wherein the storage device stores program instructions; and a processor unit connected to the bus system, wherein the processor unit processes the program instructions to record audio to form a recorded audio; convert the recorded audio to text using voice-to-text conversion; perform a comparison of the text of the voice-to-text conversion to keywords for queries using fuzzy logic to determine whether a voice command is spoken by a first person in the recorded audio; identify the voice command spoken by the first person in the recorded audio based on the comparison; determine whether the voice command spoken by the first person is directed to a virtual assistant without using a wake word to activate the virtual assistant and not to a second person by evaluating the voice command for specific language qualifiers indicative of the voice command not referencing the second person; and process the voice command using the virtual assistant without the wake word in response to the voice command not referencing the second person.
7. The computer system of claim 6 , wherein the specific language qualifiers are selected from at least one of the first person asking a question without referencing anyone, the first person issuing the voice command without referencing anyone, or the first person asking for an interface with an Internet of things device without referencing anyone.
8. The computer system of claim 6 , wherein in processing the program instructions to record the audio to form the recorded audio, the processor unit processes the program instructions to record the audio in a circular buffer.
9. The computer system of claim 6 , wherein in processing the program instructions to record the audio to form the recorded audio, the processor unit processes the program instructions to record the audio to form the recorded audio using a listening device in the computer system.
10. The computer system of claim 9 , wherein the listening device is selected from a group comprising a smart speaker, a mobile phone, a tablet computer, a television, a digital media player, a refrigerator, and an Internet appliance.
11. A computer program product for managing voice commands, the computer program product comprising a non-transitory computer-readable storage media with program code stored thereon that, when executed by a processor, performs steps of: recording audio to form a recorded audio; converting the recorded audio to text using voice-to-text conversion; performing a comparison of the text of the voice-to-text conversion to keywords for queries using fuzzy logic to determine whether a voice command is spoken by a first person in the recorded audio; identifying the voice command spoken by the first person in the recorded audio based on the comparison; determining whether the voice command spoken by the first person is directed to a virtual assistant without using a wake word to activate the virtual assistant and not to a second person by evaluating the voice command for specific language qualifiers indicative of the voice command not referencing the second person; and processing process the voice command using the virtual assistant without the wake word in response to the voice command not referencing the second person.
12. The computer program product of claim 11 , wherein recording the audio to form the recorded audio comprises: recording the audio to form the recorded audio in a circular buffer.
13. The computer program product of claim 11 , wherein recording the audio to form the recorded audio comprises: recording the audio to form the recorded audio using a listening device in a computer system.
14. The computer program product of claim 13 , wherein the listening device is selected from a group comprising a smart speaker, a mobile phone, a tablet computer, a television, a digital media player, a refrigerator, and an Internet appliance.
15. The computer program product of claim 11 , wherein the specific language qualifiers are selected from at least one of the first person asking a question without referencing anyone, the first person issuing the voice command without referencing anyone, or the first person asking for an interface with an Internet of things device without referencing anyone.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
March 9, 2018
April 13, 2021
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.